Working with Signals

Multiresolution analysis, wavelet time scattering, continuous wavelet transform, nondecimated discrete wavelet transform, Wigner-Ville distribution, mel spectrogram

Wavelet scattering enables you to produce low-variance data representations that minimize differences within a class while preserving discriminability across classes. Wavelet scattering requires few user-specified parameters to produce compact representations of data which are robust against time shifts on a scale you define. You can use these representations in conjunction with machine learning algorithms for classification and regression.

You can use the continuous wavelet transform (CWT) to generate 2-D time-frequency maps of time series data, which can be used with 2-D convolutional networks. Generating time-frequency representations for use in deep CNNs is a powerful approach for signal classification. The ability of the CWT to simultaneously capture steady-state and transient behavior in time series data makes the wavelet-based time-frequency representation particularly robust when paired with deep CNNs.

With a Signal Processing Toolbox™ license you can include the short-time Fourier transform into your machine learning and deep learning workflows. You can also use Signal Labeler (Signal Processing Toolbox) to label signals for analysis or for use in machine learning and deep learning applications. Signal Labeler saves data as labeledSignalSet objects. With a Audio Toolbox™ license you can Import and Play Audio File Data in Signal Labeler (Signal Processing Toolbox). You can also use melSpectrogram (Audio Toolbox) for feature extraction.

App

Signal Labeler

Label signal attributes, regions, and points of interest, and extract features

Funzioni

espandi tutto

Layers

`cwtLayer`	Continuous wavelet transform (CWT) layer (Da R2022b)
`modwtLayer`	Maximal overlap discrete wavelet transform (MODWT) layer (Da R2022b)
`stftLayer`	Short-time Fourier transform layer (Da R2021b)

Feature Extraction

`array2cwtfilters`	Convert deep-learning CWT filter tensor to filter bank matrix (Da R2022b)
`cwtfilterbank`	Continuous wavelet transform filter bank
`cwtfilters2array`	Convert CWT filter bank to reduced-weight tensor for deep learning (Da R2022b)
`dlcwt`	Deep learning continuous wavelet transform (Da R2022b)
`dlmodwt`	Deep learning maximal overlap discrete wavelet transform and multiresolution analysis (Da R2022a)
`dlstft`	Deep learning short-time Fourier transform (Da R2021a)
`lwt`	1-D lifting wavelet transform (Da R2021a)
`melSpectrogram`	Mel spectrogram
`modwpt`	Maximal overlap discrete wavelet packet transform
`modwt`	Maximal overlap discrete wavelet transform
`waveletScattering`	Wavelet time scattering
`wentropy`	Wavelet entropy
`wvd`	Wigner-Ville distribution and smoothed pseudo Wigner-Ville distribution

Datastores

`audioDatastore`	Datastore for collection of audio files
`augmentedImageDatastore`	Trasformare i batch per aumentare i dati dell’immagine
`imageDatastore`	Datastore for image data
`signalDatastore`	Datastore for collection of signals (Da R2020a)

Signal Labeling

`labeledSignalSet`	Create labeled signal set
`signalLabelDefinition`	Create signal label definition

Argomenti

Detect Air Compressor Sounds in Simulink Using Wavelet Scattering (DSP System Toolbox)
Use the Wavelet Scattering block and a pretrained deep learning network to classify audio signals.
Detect Anomalies in ECG Data Using Wavelet Scattering and LSTM Autoencoder in Simulink (DSP System Toolbox)
Use wavelet scattering and deep learning network to detect anomalies in ECG signals.
Radar and Communications Waveform Classification Using Deep Learning (Phased Array System Toolbox)
Classify radar and communications waveforms using the Wigner-Ville distribution (WVD) and a deep convolutional neural network (CNN).
Radar Target Classification Using Machine Learning and Deep Learning (Radar Toolbox)
Classify radar returns using machine and deep learning approaches.

Informazioni complementari

Esempi in primo piano

Acoustic Scene Recognition Using Late Fusion

Create a multi-model late fusion system for acoustic scene recognition.

Working with Signals

App

Funzioni

Layers

Feature Extraction

Datastores

Signal Labeling

Argomenti

Informazioni complementari

Esempi in primo piano

Acoustic Scene Recognition Using Late Fusion

Air Compressor Fault Detection Using Wavelet Scattering

Anomaly Detection Using Autoencoder and Wavelets

Classify Time Series Using Wavelet Analysis and Deep Learning

Crack Identification from Accelerometer Data

Detect Anomalies Using Wavelet Scattering with Autoencoders

Time-Frequency Convolutional Network for EEG Data Classification

Fault Detection Using Wavelet Scattering and Recurrent Deep Networks

GPU Acceleration of Scalograms for Deep Learning

Human Health Monitoring Using Continuous Wave Radar and Deep Learning

Signal Classification Using Wavelet-Based Features and Support Vector Machines

Signal Recovery with Differentiable Scalograms and Spectrograms

Spoken Digit Recognition with Wavelet Scattering and Deep Learning

Time-Frequency Feature Embedding with Deep Metric Learning

Wavelet Time Scattering Classification of Phonocardiogram Data

Wavelet Time Scattering for ECG Signal Classification